search_google
AI agents call search_google to retrieve information from Jeneen's MCP Agent without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Google search is fundamentally a Read operation—it retrieves publicly available information without modifying, deleting, or executing code. Severity is medium rather than low because search results could be used to gather reconnaissance for targeted attacks or social engineering, and search query logs may reveal sensitive information about the requester's intent.
From the tool's definition Tool name 'search_google' indicates a Google search capability as mentioned in the server description. Searches retrieve and query data with no side effects.
Attacks that exploit this kind of access
search_google. It is categorised as a Read tool in the Jeneen's MCP Agent MCP Server, which means it retrieves data without modifying state.
Register the Jeneen's MCP Agent MCP server in PolicyLayer and add a rule for search_google: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Jeneen's MCP Agent. Nothing to install.
search_google is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the search_google rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for search_google. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
search_google is provided by the Jeneen's MCP Agent MCP server (jeneen24/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →